{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:31:35Z","timestamp":1761931895382,"version":"build-2065373602"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Abu Dhabi Investment Authority"},{"DOI":"10.13039\/501100004070","name":"Khalifa University of Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004832","name":"Khalifa University of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004832","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3625120","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T18:05:43Z","timestamp":1761588343000},"page":"184059-184070","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Modal Understanding of FOMC Press Conferences for Question Generation via Visual and Textual Cues"],"prefix":"10.1109","volume":"13","author":[{"given":"Khaled","family":"Alnuaimi","sequence":"first","affiliation":[{"name":"Abu Dhabi Investment Authority (ADIA), Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2960-2972","authenticated-orcid":false,"given":"Mohamad","family":"Alansari","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1646-7919","authenticated-orcid":false,"given":"Mohammed","family":"Salah","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2826-1515","authenticated-orcid":false,"given":"Hasan","family":"Al Marzouqi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1386-5372","authenticated-orcid":false,"given":"Andreas","family":"Henschel","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/14614456241276762"},{"key":"ref2","article-title":"Analyzing fomc minutes: Accuracy and constraints of language models","author":"Kim","year":"2024","journal-title":"arXiv:2304.10164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3537822"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/jfir.12199"},{"key":"ref5","article-title":"Financebench: A new benchmark for financial question answering","author":"Islam","year":"2023","journal-title":"arXiv:2311.11944"},{"key":"ref6","article-title":"FinBERT-QA: Financial question answering with pre-trained BERT language models","author":"Yuan","year":"2025","journal-title":"arXiv:2505.00725"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.421"},{"issue":"3","key":"ref8","first-page":"49","article-title":"A new measure of central bank transparency and implications for the effectiveness of monetary policy","volume":"19","author":"Acosta","year":"2023","journal-title":"Int. J. Central Banking"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfineco.2022.04.005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/S0022109018001357"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.qref.2024.03.014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11156-024-01318-9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/00036846.2024.2322573"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2016-186"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5209\/rev_clac.2014.v59.46708"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2018EDP7199"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.340"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-024-02826-0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89363-7_25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.328"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3468889"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-3442-9_42"},{"key":"ref24","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref25","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref28","article-title":"Sa2 VA: Marrying SAM2 with LLaVA for dense grounded understanding of images and videos","author":"Yuan","year":"2025","journal-title":"arXiv:2501.04001"},{"key":"ref29","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref30","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.36871\/ek.up.p.r.2024.12.08.009"},{"key":"ref32","first-page":"29","article-title":"Using TF-IDF to determine word relevance in document queries","volume-title":"Proc. 1st Instructional Conf. Mach. Learn.","volume":"242","author":"Ramos"},{"key":"ref33","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref34","article-title":"VideoGLaMM: A large multimodal model for pixel-level visual grounding in videos","author":"Munasinghe","year":"2024","journal-title":"arXiv:2411.04923"},{"key":"ref35","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","volume-title":"arXiv:2404.14219","author":"Abdin","year":"2024"},{"key":"ref36","article-title":"Qwen2.5 technical report","volume-title":"arXiv:2412.15115","author":"Yang","year":"2024"},{"volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%ChatGPT Quality","year":"2023","author":"Chiang","key":"ref37"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11216342.pdf?arnumber=11216342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:13:28Z","timestamp":1761930808000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11216342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3625120","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}